© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163208
    Prev
    Next
    INDEX
    Explanations

    sheer numbers and breadth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infections
    0.38
    natives
    0.35
    =>{
    0.34
     KA
    0.33
    spraak
    0.33
    oscale
    0.33
    éhez
    0.32
    ike
    0.32
     erased
    0.32
    㑒
    0.32
    POSITIVE LOGITS
     Wra
    0.40
     Wrap
    0.36
    য
    0.35
     ቤ
    0.34
     proxy
    0.34
    करण
    0.33
     wraps
    0.33
    izado
    0.33
    শ্বর
    0.33
    물
    0.33
    Activations Density 0.004%

    No Known Activations